Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official

fanduel_racing_search

Search FanDuel Racing by name to find matching horses, jockeys, trainers, and owners, with paged results plus each horse’s last-start date, race, and track.

Instructions

FanDuel Racing search by name. Finds horses, jockeys, trainers and owners whose name contains the text (3 to 64 characters), with a horse's id and birth year and the date, race and track of each one's last start. Use a horse's id with the horse route. The service returns every match (several hundred owners for a common surname), so the list is paged here: horses first, then jockeys, trainers and owners, each group sorted by sort and order. Jockeys, trainers and owners have no id.

Input Schema

NameRequiredDescriptionDefault
qYesName text, 3 to 64 characters; matching is case-insensitive
pageNoPage number, from 1; default 1, at most 10000
sortNoSort within each kind; default `name`
typeNoKeep one kind (any other value silently finds nothing upstream, so it returns `400`)
limitNoItems per page, 1 to 200; default 50
orderNo`asc` or `desc`; default `asc`

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.17.16

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden and does well: it discloses that all matches come back (hundreds of owners for a common surname), that results are paged with horses first and then jockeys/trainers/owners, and that only horses carry an id. It doesn't say whether `type` changes the group ordering or what an empty result looks like.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose, then the returned fields, then the sibling routing, then paging. Dense but every sentence carries information; the parenthetical on hundreds of owners is the only borderline element, and it justifies the paging sentence.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema, so the description correctly spells out the shape of a hit (id, birth year, last start date/race/track) and the paging protocol. With six parameters and no annotations, the only small gaps are empty-result behavior and how `type` interacts with the group ordering.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, but the description adds non-obvious semantics: `sort` and `order` apply within each kind group, and the group ordering itself is fixed (horses first). That is information the schema does not convey. It doesn't clarify how `page` interacts with mixed groups.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource (name search over FanDuel Racing) and scopes the entity kinds covered: horses, jockeys, trainers, owners. It also names the follow-on sibling route (`horse`) so the agent can distinguish this lookup from the detail tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly tells the agent to take a horse's `id` and use the `horse` route, and explains paging is required because the service returns every match. No guidance on when to prefer `type` filtering versus letting the mixed list page through, and no mention of the sibling `fanduel_racing_filters` tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools